Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3765 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.8189. Min Act: -0.0001

Data Index: 895194 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7128. Min Act: -0.0001

Data Index: 677850 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6698. Min Act: -0.0002

Data Index: 1355476 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6845. Min Act: -0.0001

Data Index: 1241830 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6718. Min Act: -0.0001

Data Index: 181239 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6625. Min Act: -0.0001

Data Index: 881850 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6230. Min Act: -0.0002

Data Index: 1061509 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6180. Min Act: -0.0001

Data Index: 738840 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5808. Min Act: -0.0001

Data Index: 1193124 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6568. Min Act: -0.0002

Data Index: 1094109 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6282. Min Act: -0.0001

Data Index: 1089097 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6070. Min Act: -0.0001

Data Index: 36045 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6220. Min Act: -0.0001

Data Index: 1637881 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6166. Min Act: -0.0002

Data Index: 842254 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6141. Min Act: -0.0001

Data Index: 256660 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5776. Min Act: -0.0002

Data Index: 1215334 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5920. Min Act: -0.0001

Data Index: 1119095 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6316. Min Act: -0.0001

Data Index: 387328 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6096. Min Act: -0.0002

Data Index: 381845 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5788. Min Act: -0.0001

Data Index: 1281452 (C4 (Web Text))

Max Activating Token Index: 398